Perturbing the Phase: Analyzing Adversarial Robustness of Complex-Valued Neural Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Eilers, Florian, Duhme, Christof, Jiang, Xiaoyi
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917254474498048
author Eilers, Florian
Duhme, Christof
Jiang, Xiaoyi
author_facet Eilers, Florian
Duhme, Christof
Jiang, Xiaoyi
contents Complex-valued neural networks (CVNNs) are rising in popularity for all kinds of applications. To safely use CVNNs in practice, analyzing their robustness against outliers is crucial. One well known technique to understand the behavior of deep neural networks is to investigate their behavior under adversarial attacks, which can be seen as worst case minimal perturbations. We design Phase Attacks, a kind of attack specifically targeting the phase information of complex-valued inputs. Additionally, we derive complex-valued versions of commonly used adversarial attacks. We show that in some scenarios CVNNs are more robust than RVNNs and that both are very susceptible to phase changes with the Phase Attacks decreasing the model performance more, than equally strong regular attacks, which can attack both phase and magnitude.
format Preprint
id arxiv_https___arxiv_org_abs_2602_06577
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Perturbing the Phase: Analyzing Adversarial Robustness of Complex-Valued Neural Networks
Eilers, Florian
Duhme, Christof
Jiang, Xiaoyi
Machine Learning
Artificial Intelligence
Complex-valued neural networks (CVNNs) are rising in popularity for all kinds of applications. To safely use CVNNs in practice, analyzing their robustness against outliers is crucial. One well known technique to understand the behavior of deep neural networks is to investigate their behavior under adversarial attacks, which can be seen as worst case minimal perturbations. We design Phase Attacks, a kind of attack specifically targeting the phase information of complex-valued inputs. Additionally, we derive complex-valued versions of commonly used adversarial attacks. We show that in some scenarios CVNNs are more robust than RVNNs and that both are very susceptible to phase changes with the Phase Attacks decreasing the model performance more, than equally strong regular attacks, which can attack both phase and magnitude.
title Perturbing the Phase: Analyzing Adversarial Robustness of Complex-Valued Neural Networks
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2602.06577